Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    HTML tags and structured data

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     chees
    0.71
     hogs
    0.69
     thanksgiving
    0.69
     firefighter
    0.68
     bem
    0.68
     raisin
    0.67
     Gaelic
    0.67
     popular
    0.65
     ear
    0.65
    础
    0.64
    POSITIVE LOGITS
    tex
    1.75
    mml
    1.47
    asci
    1.42
    font
    1.24
    img
    1.23
    br
    1.20
    span
    1.18
    wbr
    1.10
    ...>
    1.10
    script
    1.00
    Act Density 0.020%

    No Known Activations